AISafety-SafeRL 2023
Artificial Intelligence Safety and Safe Reinforcement Learning 2023

Table of Contents

• Preface
  Summary: There were 19 papers submitted for peer-review to this workshop. Out of these, 10 papers were accepted for this volume.

Session 1: Robustness of AI via OoD and Unknown-Unknowns Dectection

• Diffusion Denoised Smoothing for Certified and Adversarial Robust Out Of Distribution
  Nicola Franco, Daniel Korth, Jeanette Miriam Lorenz, Karsten Roscher, Stephan Günnemann
• Unsupervised Unknown Unknown Detection in Active Learning
  Prajit T. Rajendran, Huascar Espinoza, Agnes Delaborde, Chokri Mraidha

Session 2: AI Robustness, Adversarial Attacks and Reinforcemnt Learning

• PerCBA: Persistent Clean-label Backdoor Attacks on Semi-Supervised Graph Node Classification
  Xiao Yang, Gaolei Li, Chaofeng Zhang, Meng Han, Wu Yang
• Distribution-restrained Softmax Loss for the Model Robustness
  Chen Li, Hao Wang, Jinzhe Jiang, Xin Zhang, Yaqian Zhao, Weifeng Gong
• Fear Field: Adaptive constraints for safe environment transitions in Shielded Reinforcement Learning
  Haritz Odriozola-Olalde, Nestor Arana-Arexolaleiba, Maider Zamalloa, Jon Perez-Cerrolaza, Jokin Arozamena-Rodríguez

Session 3: AI Governance and Policy/Value Alignment

• An open source perspective on AI and alignment with the EU AI Act
  Diego Calanzone, Andrea Coppari, Riccardo Tedoldi, Giulia Olivato, Carlo Casonato

Session 4: Safe RL

• Risk-sensitive Actor-free Policy via Convex Optimisation
  Ruoqi Zhang, Jens Sjölund

Session 5: AI Trustworthiness, Explainability and Testing

• Empirical Optimal Risk to Quantify Model Trustworthiness for Failure Detection
  Shuang Ao, Stefan Rueger, Advaith Siddharthan
• Weight-based Semantic Testing Approach for Deep Neural Networks
  Amany Alshareef, Nicolas Berthier, Sven Schewe, Xiaowei Huang
• AI for Safety: How to use Explainable Machine Learning Approaches for Safety Analyses
  Iwo Kurzidem, Simon Burton, Philipp Schleiss